数据集与基准论文趋势 2023–2026

新数据集与评测协议

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 5,856 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

数据集与基准论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
2023227162166382937
20244482163183641,346
20256374191893371,582
20266236352754581,991

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部数据集与基准论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 5,852 篇，第 13 / 118 页

  1. ICLR 2026DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
  2. ICLR 2026DELTA-Code: How RL Unlocks and Transfers New Programming Algorithms in LLMs
  3. ICLR 2026Demystifying Deep Search: A Holistic Evaluation with Hint-free Multi-Hop Questions and Factorised Metrics
  4. ICLR 2026DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning
  5. ICLR 2026Detecting Data Contamination in LLMs via In-Context Learning
  6. ICLR 2026DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
  7. ICLR 2026DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning
  8. ICLR 2026Diffusion Models as Dataset Distillation Priors
  9. ICLR 2026DISCO: Diversifying Sample Condensation for Accelerating Model Evaluation
  10. ICLR 2026DiscoX: Benchmarking Discourse-Level Translation in Expert Domains
  11. ICLR 2026DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstruction
  12. ICLR 2026Do 3D Large Language Models Really Understand 3D Spatial Relationships?
  13. ICLR 2026Do LLM Agents Know How to Ground, Recover, and Assess? Evaluating Epistemic Competence in Information-Seeking Agents
  14. ICLR 2026Do LLMs Forget What They Should? Evaluating In-Context Forgetting in Large Language Models
  15. ICLR 2026Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?
  16. ICLR 2026Don't Forget Its Variance! The Minimum Path Variance Principle for Accurate and Stable Score-Based Models
  17. ICLR 2026DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving
  18. ICLR 2026DUET: DISTILLED LLM UNLEARNING FROM AN EFFICIENTLY CONTEXTUALIZED TEACHER
  19. ICLR 2026EarthSE: A Benchmark Evaluating Earth Scientific Exploration Capability for Large Language Models
  20. ICLR 2026Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
  21. ICLR 2026EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language Models
  22. ICLR 2026EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements
  23. ICLR 2026EditBench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits
  24. ICLR 2026EditReward: A Human-Aligned Reward Model for Instruction-Guided Image Editing
  25. ICLR 2026EdiVal-Agent: An Object-Centric Framework for Automated, Fine-Grained Evaluation of Multi-Turn Editing
  26. ICLR 2026EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video
  27. ICLR 2026EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
  28. ICLR 2026EgoTwin: Dreaming Body and View in First Person
  29. ICLR 2026Emergent Misalignment is Easy, Narrow Misalignment is Hard
  30. ICLR 2026EmoPrefer: Can Large Language Models Understand Human Emotion Preferences?
  31. ICLR 2026Enhanced Generative Model Evaluation with Clipped Density and Coverage
  32. ICLR 2026Enhancing Agentic Search via Data Synthesis on Hierarchical Constraint Satisfaction
  33. ICLR 2026Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
  34. ICLR 2026Enhancing Learning with Noisy Labels via Rockafellian Relaxation
  35. ICLR 2026Entering the Era of Discrete Diffusion Models: A Benchmark for Schrödinger Bridges and Entropic Optimal Transport
  36. ICLR 2026ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
  37. ICLR 2026Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
  38. ICLR 2026Evaluating Cross-Modal Reasoning Ability and Problem Charactaristics with Multimodal Item Response Theory
  39. ICLR 2026Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
  40. ICLR 2026Evaluating SAE interpretability without generating explanations
  41. ICLR 2026Evaluating Text Creativity across Diverse Domains: a Dataset and Large Language Model Evaluator
  42. ICLR 2026Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
  43. ICLR 2026EXP-Bench: Can AI Conduct AI Research Experiments?
  44. ICLR 2026Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis
  45. ICLR 2026ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists
  46. ICLR 2026ExpGuard: LLM Content Moderation in Specialized Domains
  47. ICLR 2026Explainable $ K $-means Neural Networks for Multi-view Clustering
  48. ICLR 2026Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
  49. ICLR 2026Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
  50. ICLR 2026Exploring Real-Time Super-Resolution: Benchmarking and Fine-Tuning for Streaming Content

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查数据集与基准在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "dataset-and-benchmarks"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇数据集与基准论文？
共 5,856 篇，按年份分别是 2023 年 937 篇、2024 年 1,346 篇、2025 年 1,582 篇、2026 年 1,991 篇。
NeurIPS 2026 有多少篇数据集与基准论文？
NeurIPS 2026 有 623 篇数据集与基准论文，上一届是 637 篇。
ICLR 2026 有多少篇数据集与基准论文？
ICLR 2026 有 635 篇数据集与基准论文，上一届是 419 篇。
ICML 2026 有多少篇数据集与基准论文？
ICML 2026 有 275 篇数据集与基准论文，上一届是 189 篇。
CVPR 2026 有多少篇数据集与基准论文？
CVPR 2026 有 458 篇数据集与基准论文，上一届是 337 篇。
哪个会议的数据集与基准论文最多？
NeurIPS，2023–2026 年共 1,935 篇。

「效率与系统」下的其他主题